WorldDiT: A Unified Architecture for World and Action Modeling

We’re releasing WorldDiT, a pareto frontier model architecture bringing world and robot action modeling into one compact diffusion transformer, without relying on a large pretrained VLM action backbone.

WorldDiT in action

• At 399 million total parameters, WorldDiT lies on the reported LIBERO Pareto frontier for model size and mean success.

• Among publicly released methods in the comparison that do not use a large pretrained VLM action backbone, it reports the highest mean success.

• WorldDiT unifies future visual world state prediction with continuous robot action generation in a single diffusion transformer.

If you use WorldDiT in your research, feel free to cite the paper.